A Workbench for Discovering Task-Specific Theories of Learning
Abstract
Very little of our cognitive behavior (as opposed to more peripheral behaviors) is determined by the fixed, unchangeable parts of our mind. Cognitive behaviors seem to be determined by our knowledge and the environment itself. Thus, recent work in A1 on developing models of the fixed part of the mind (the cognitive architecture) will not be of much use to educators who wish to perform a cognitive task analysis of their subject matter before designing instruction for it. However, it seems technically feasible, given the state of the art in Machine Learning, to build semi-automated data analysis packages that can be added to a cognitive architecture, thus creating a 'workbench' for performing cognitive task analysis. Such tools becomes particularly interesting when used to analyze not only the experts' understanding of the subject matter, but to trace the development of a student's understanding. In this application, the workbench can lead to task-specific theories of learning which are much more informative to educators than most learning theories have been. Keywords: Cognitive task analysis, Instructional design, Cognitive modelling, Learning.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 03, 1989
- Accession Number
- ADA222430
Entities
People
- Kurt A. Vanlehn
Organizations
- Carnegie Mellon University